Generalization and Expressivity for Deep Nets
This work provides a theoretical foundation for deep learning by bridging expressivity and generalization, which is incremental as it builds on existing measurements but combines them to show advantages.
The authors tackled the theoretical challenge of explaining deep learning's success by simultaneously addressing both expressivity and generalization, constructing a two-hidden-layer deep net with excellent localized and sparse approximation that achieves near-optimal learning rates for empirical risk minimization.
Along with the rapid development of deep learning in practice, the theoretical explanations for its success become urgent. Generalization and expressivity are two widely used measurements to quantify theoretical behaviors of deep learning. The expressivity focuses on finding functions expressible by deep nets but cannot be approximated by shallow nets with the similar number of neurons. It usually implies the large capacity. The generalization aims at deriving fast learning rate for deep nets. It usually requires small capacity to reduce the variance. Different from previous studies on deep learning, pursuing either expressivity or generalization, we take both factors into account to explore the theoretical advantages of deep nets. For this purpose, we construct a deep net with two hidden layers possessing excellent expressivity in terms of localized and sparse approximation. Then, utilizing the well known covering number to measure the capacity, we find that deep nets possess excellent expressive power (measured by localized and sparse approximation) without enlarging the capacity of shallow nets. As a consequence, we derive near optimal learning rates for implementing empirical risk minimization (ERM) on the constructed deep nets. These results theoretically exhibit the advantage of deep nets from learning theory viewpoints.